This preview shows page 1. Sign up to view the full content.
Unformatted text preview: signed to node t T is denoted by (t). For 01 loss, the class assignment rule is: (t) = arg max p(j  t) .
j Jia Li http://www.stat.psu.edu/jiali Classification/Decision Trees (I) The resubstitution estimate r (t) of the probability of misclassification, given that a case falls into node t is r (t) = 1  max p(j  t) = 1  p((t)  t) .
j Denote R(t) = r (t)p(t). The resubstitution estimate for the overall misclassification rate R(T ) of the tree classifier T is: R(T ) = R(t) .
~ tT Jia Li http://www.stat.psu.edu/jiali Classification/Decision Trees (I) Proposition: For any split of a node t into tL and tR , R(t) R(tL ) + R(tR ) . Proof: Denote j = (t). p(j  t) = p(j , tL  t) + p(j , tR  t) = p(j  tL )p(tL  t) + p(j  tR )p(tR  t) = pL p(j  tL ) + pR p(j  tR )
j j pL max p(j  tL ) + pR max p(j  tR ) Jia Li http://www.stat.psu.edu/jiali Classification/Decision Trees (I) Hence, r (t) = 1  p(j  t) 1  pL max p(j  tL ) + pR max p(j  tR )
j j j j = pL (1  max p(j  tL )) + pR (1  max p(j  tR )) = pL r (tL ) + pR r (tR ) Finally, R(t) = p(t)r (t) p(t)pL r (tL ) + p(t)pR r (tR ) = p(tL )r (tL ) + p(tR )r (tR ) = R(tL ) + R(tR )
Jia Li http://www.stat.psu.edu/jiali Classification/Decision Trees (I) Digit Recognition Example (CART) The 10 digits are shown by different onoff combinations of seven horizontal and vertical lights. Each digit is represented by a 7dimensional vector of zeros and ones. The ith sample is xi = (xi1 , xi2 , ..., xi7 ). If xij = 1, the jth light is on; if xij = 0, the jth light is off.
http://www.stat.psu.edu/jiali Jia Li Classification/Decision Tr...
View
Full
Document
This note was uploaded on 02/04/2012 for the course STAT 557 taught by Professor Jiali during the Fall '09 term at Penn State.
 Fall '09
 JIALI
 Statistics

Click to edit the document details